AI 驱动自动化控制：从 “智” 造到 “慧” 控的跃迁

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split

# 模拟生产数据，5个输入特征，如温度、压力、流量、转速、原料配比
X = np.random.rand(200, 5) 
# 输出，如产品质量，受输入特征影响并添加噪声
y = 1.5 * X[:, 0] + 2.5 * X[:, 1] + 3 * X[:, 2] + 1.8 * X[:, 3] + 2.2 * X[:, 4] + np.random.randn(200) 

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
mse = np.mean((y_pred - y_test) ** 2)
print(f"生产过程优化模型均方误差: {mse}")

import tensorflow as tf
import numpy as np

# 模拟设备多源信号数据，假设振动、温度、电流3种信号，各1000个时间点
vibration_data = np.random.rand(1000, 1) 
temperature_data = np.random.rand(1000, 1) + 25
current_data = np.random.rand(1000, 1) * 5

data = np.concatenate([vibration_data, temperature_data, current_data], axis = 1)

def create_dataset(data, time_steps=15):
    X, y = [], []
    for i in range(len(data) - time_steps):
        X.append(data[i:i + time_steps])
        y.append(data[i + time_steps])
    return np.array(X), np.array(y)

X, y = create_dataset(data)
train_size = int(len(X) * 0.8)
X_train, X_test = X[:train_size], X[train_size:]
y_train, y_test = y[:train_size], y[train_size:]

model = tf.keras.Sequential([
    tf.keras.layers.LSTM(64, input_shape=(15, 3)),
    tf.keras.layers.Dense(3)
])
model.compile(optimizer='adam', loss='mse')
model.fit(X_train, y_train, epochs=60, batch_size=32)
y_pred = model.predict(X_test)
mse = np.mean((y_pred - y_test) ** 2)
print(f"设备故障诊断模型均方误差: {mse}")

import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import LabelEncoder

# 模拟交通流量数据，包含时间、流量、天气状况
data = {
    '时间': pd.date_range(start='2023-01-01', periods=150, freq='H'),
    '流量': np.random.randint(100, 600, 150),
    '天气': np.random.choice(['晴', '雨', '阴'], 150)
}
df = pd.DataFrame(data)

# 提取时间特征，如小时、星期几
df['小时'] = df['时间'].dt.hour
df['星期几'] = df['时间'].dt.dayofweek

# 对天气进行编码
encoder = LabelEncoder()
df['天气编码'] = encoder.fit_transform(df['天气'])

X = df[['小时', '星期几', '天气编码']]
y = df['流量']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model = RandomForestRegressor(n_estimators = 100)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
mse = np.mean((y_pred - y_test) ** 2)
print(f"交通流量预测模型均方误差: {mse}")

import torch
from torchvision.models.detection import yolov5
from torchvision import transforms
from PIL import Image

model = yolov5()
model.load_state_dict(torch.load('yolov5s.pt'))
model.eval()

def predict_image(image_path):
    img = Image.open(image_path)
    transform = transforms.Compose([
        transforms.Resize((640, 640)),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    ])
    img = transform(img).unsqueeze(0)
    with torch.no_grad():
        outputs = model(img)
    return outputs

image_path = 'test_image.jpg'
result = predict_image(image_path)
print("图像目标识别结果:", result)

import numpy as np
from sklearn.mixture import GaussianMixture

# 模拟用户灯光使用习惯数据，150个样本，3个特征（时间、亮度、使用时长）
data = np.random.rand(150, 3) 

gmm = GaussianMixture(n_components=4)
gmm.fit(data)
labels = gmm.predict(data)

print("用户灯光使用习惯聚类结果:", labels)

import pandas as pd
from statsmodels.tsa.arima.model import ARIMA

# 模拟家居能源消耗数据，包含时间、空调、冰箱、照明能耗
data = {
    '时间': pd.date_range(start='2023-01-01', periods=120, freq='H'),
    '空调功率': np.random.randint(1000, 3500, 120),
    '冰箱功率': np.random.randint(100, 350, 120),
    '照明功率': np.random.randint(50, 250, 120)
}
df = pd.DataFrame(data)

df['总能源消耗'] = df['空调功率'] + df['冰箱功率'] + df['照明功率']

# 对总能源消耗进行ARIMA建模预测
train_data = df['总能源消耗'][:100]
test_data = df['总能源消耗'][100:]

model = ARIMA(train_data, order=(1, 1, 1))
model_fit = model.fit()
forecast = model_fit.get_forecast(steps = len(test_data))
forecast_mean = forecast.predicted_mean
mse = np.mean((forecast_mean - test_data) ** 2)
print(f"家居能源消耗预测均方误差: {mse}")